How to export the model to torchscript？

[simba0703]

How to export the model to torchscript？

[innerlee]

Hi we haven't provide tools yet. Please request the feature here #9 to help us prioritize.

[alicera]

Can the network export the onnx including decode ? like HeatmapParser function

[greg-is-kub]

requesting module to the DJ programming team as well, keep up the good work guys you rock

[chophilip21]

any update on this?

[den-run-ai]

onnx conversion works, but torchscript conversion fails due to custom sub-class of pytorch

[rtaylo45]

I know im a little late on this thread but i was having a similar issue to @alicera for exporting a module using onnx. The model only returns the heat map and not the decoded keypoints. Is this still an issue? If not, can someone point me to an onnx example?

[Monalsingh]

I also want to know, how to convert mmpose models to onnx. Does anyone have an example code?

[ly015]

@Monalsingh @rtaylo45 Now we have MMDeploy to support model export and deployment for MMPose. An example is provided in MMDeploy documents.

[AshvantSelvam]

Would like to have Tracing support for mmPose models.
I have been able to successfully use 'torch2torchscript' under mmdeploy.apis to trace mmSegmentation Models. However, using the same on mmPose (tried configs under dekr and associative+embedding) with the following mmdeploy config: '\mmdeploy\configs\mmpose\pose-detection_torchscript.py' would throw the following error:

File "mmdetection\mmpose\mmpose\datasets\pipelines\shared_transform.py", line 176, in call
meta[key_tgt] = results[key_src]

KeyError: 'flip_index'

Added this to the feature request page. Posting here to see if there are any possible workarounds.

[rookiez7]

Now,Can export the model to torchscript？